© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 55302
    Prev
    Next
    INDEX
    Explanations

    kombucha and cabbage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åī¡
    -0.12
    åĩĢ
    -0.10
    ctic
    -0.09
    .TypeOf
    -0.09
    inne
    -0.09
    æ´Ħ
    -0.09
    ä¸įåĬ¨
    -0.09
    ively
    -0.09
    hp
    -0.09
    arily
    -0.08
    POSITIVE LOGITS
    ys
    0.09
    çĶŁåij½åĬĽ
    0.09
    åĩłçĤ¹
    0.09
    åĪĨãģij
    0.09
    使èĢħ
    0.08
    æ¢Ĩ
    0.08
    ä¸Ģ个æĺŁæľŁ
    0.08
    ä¼¼
    0.08
    æģĥ
    0.08
    éħĿ
    0.08
    Activations Density 0.005%

    No Known Activations